Artificial Neural Networks as Tool to Solve the Schrödinger Equation

Nieto-Chaupis H. · Proceedings - 2025 8th Asia Conference on Cognitive Engineering and Intelligent Interaction, CEII 2025 (2025) · DOI: 10.1109/ceii67787.2025.00020

Resumen

Inside the framework of paradigm of Machine Learning and its branch called artificial neural network, some topologies have been used to solve in a systematic manner the well-known Schrödinger equation. Therefore, it was found a concrete scheme that allows to solve the case of free particle in a box. In contrast to standard methods of solution, the boundary's conditions have emerged to play a crucial role under the present approach. Although the paper exposes a concrete topology, it is clear that it can be generalized for other cases either simple or complex Hamiltonians. The paper demonstrates that machine learning would constitute a robust computational tool to be successfully applied in basic sciences like physics, with a clear extension to mathematics and related areas.

Instituciones: Universidad Autónoma del Perú